[flagged]
DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
291–300 of 325 posts
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#292[flagged]
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#293As someone who has been writing harnesses for a year: the people at opencode etc aren't stupid, when they decide to break the prefix cache [usually partially] it's always because they've tested it and it gives better results overall. If you think that dsv4 behaves differently enough from the aggregate of other models, submit a PR with a patch to special case that to your harness of choice with evidence. Just blindly…
Is "harness" in this context ~= "agent"?
I think agent = harness + model.
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#294Earlier quoted context omitted.
(Zero reason to defend Anthropic.) I’ve gone that route. I really wanted to stop using Claude, but Deepseek v4 Pro and Kimi 2.6 didn’t do the job. For a lot of coding tasks or well-specced plans, maybe… but then that’s a plan made by Opus anyway. Even Sonnet is sometimes not worth the trouble. Opus is very thorough and reviews its own mistakes quite well. Catches a lot of edge cases. I’m not saying we shouldn’t try o…
/advisor is like the old /opusplan mode but for running tasks not just pre-planning. It can work nicely with Sonnet as the main agent and escalates to Opus as needed.
Advisor-mode has been very helpful indeed, I can now plan with Opus, have Haiku code, and escalate back to Opus for review. It’s a decent flow for Pro subscribers trying to max their usage. But as I’ve said above, sometimes it’s not worth it: Sonnet and Haiku can produce stuff that’s not worth reviewing.
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#295Earlier quoted context omitted.
It’s sad to see companies not spending a bit more on design. Sure, ai will help you get something decent out fast. But there’s a threshold where design becomes an indicator of trust. Especially for b2b software that tailor to large corps. Good design, character, adds directly to the bottom line.
> It’s sad to see companies… The article is about an open source agent harness, Reasonix, that is built to leverage the DeepSeek native api. There’s no company here. No design budget. These people are graciously sharing a project they made in their free time.
I agree. I didn’t mean to be too critical. But if they’d made something simpler, I think it would save them tokens and end up more likely to convince their target audience of developers.
(The series of ‘motherfucking websites’ comes to mind, they were all very readable and simple, even if satire.)
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#296Earlier quoted context omitted.
The last time I heard about something like this, it was Claude Code intentionally injecting random strings to break caching when you're not using a Claude model. Aside from that kind of intentional sabotage, I don't think any coding agent would just ignore prefix caching.
I haven't heard about this, could you please share more info, some reference on that Claude Code intentional bug?
I'm not sure what the mechanism is, but I've definitely had Claude refuse to work on sessions that were touched by other models. Some kind of integrity check failure. Resetting the session back to the point before I used the other model fixed the problem.
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#297Earlier quoted context omitted.
> I wrote a tiny little bridge so I could use DeepSeek V4 Pro via Codex Can you share the bridge. DeepSeek v4 is awesome paired with claude-code or opencode. I found that claude code costs me less than opencode and I am presuming this is due to a better engineered harness.
I don't think DeepSeek v4 Flash is as good as Claude for relatively complex tasks. I ran with DeepSeek for a week, giving it the same sort of tasks that Claude normally does, and then ran Claude and asked it to continue. It found a whole bunch of things that had been "overlooked" by DeepSeek, and spent some time fixing them before wanting to move on. DeepSeek is good, Claude is better, at least IMHO. Deepseek is a lo…
[dead]
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#298[dead]
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#299As someone who has been writing harnesses for a year: the people at opencode etc aren't stupid, when they decide to break the prefix cache [usually partially] it's always because they've tested it and it gives better results overall. If you think that dsv4 behaves differently enough from the aggregate of other models, submit a PR with a patch to special case that to your harness of choice with evidence. Just blindly…
Are there any learning resources you'd recommend on writing harnesses? I'm interested in doing a non-coding one, but not really sure where to start.
My agent wrote a pile of very interesting articles at wasnotwas.com I have been a bit quiet there for a bit, but it covers lots of areas that are very interesting to harness builders (albeit less interesting to the general public)
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#300[flagged]